© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 19689
    Prev
    Next
    INDEX
    Explanations

    code class program

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    decoderesearch/qwen-3.5-saes/qwen-3.5-4b
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    èħĶ
    -0.06
    çĸı
    -0.06
     bout
    -0.06
    å¤ĸåIJij
    -0.06
    elv
    -0.06
    ISTER
    -0.05
    ahoo
    -0.05
    åĩĨ
    -0.05
     اÙĦÙħاج
    -0.05
    uling
    -0.05
    POSITIVE LOGITS
    ائÙħ
    0.06
    ây
    0.06
    gear
    0.05
    æĺ¯ä¸Ģ缴
    0.05
    æŁĶ软çļĦ
    0.05
    kest
    0.05
    astique
    0.05
    缮ãģ§
    0.05
    ennes
    0.05
    ÑįнеÑĢго
    0.05
    Activations Density 0.002%

    No Known Activations